PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition.
Title resolution pending
7 Pith papers cite this work, alongside 18 external citations. Polarity classification is still indexing.
7
Pith papers citing it
18
external citations · external index
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
An FPGA implementation of a neuromorphic auditory sensor plus graph neural network achieves 87.43% accuracy on Google Speech Commands v2 with sub-35 µs latency and 1.12 W power.
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
A recurrent SNN with D=41 heterogeneous delays per synapse stores and recalls 16 arbitrary spike patterns at mean F1=1.0 by chaining overlapping Spiking Motifs.
A dual memory pathway spiking network with near-memory hardware achieves long-sequence accuracy using 40-60% fewer parameters and delivers over 4X throughput plus 5X energy efficiency gains.
FPGA hardware for event-graph NN achieves 92.7% accuracy on SHD dataset with fewer parameters than SOTA while outperforming prior FPGA SNNs.
citing papers explorer
-
Predictive Coding Light+: learning to predict visual sequences with spike timing-dependent plasticity and synaptic delays
PCL+ spiking network learns recurrent connections with delays via STDP to retain recent visual inputs and predict future ones, reproducing cortical sequence learning and filling missing data in gesture recognition.
-
End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
An FPGA implementation of a neuromorphic auditory sensor plus graph neural network achieves 87.43% accuracy on Google Speech Commands v2 with sub-35 µs latency and 1.12 W power.
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
-
Scalable neuromorphic computing from autonomous spiking dynamics in a clockless reconfigurable chip
Clockless FPGA circuits produce autonomous spiking neuron networks that achieve competitive audio classification accuracy with significantly lower power than conventional digital implementations.
-
Working Memory in a Recurrent Spiking Neural Networks With Heterogeneous Synaptic Delays
A recurrent SNN with D=41 heterogeneous delays per synapse stores and recalls 16 arbitrary spike patterns at mean F1=1.0 by chaining overlapping Spiking Motifs.
-
Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
A dual memory pathway spiking network with near-memory hardware achieves long-sequence accuracy using 40-60% fewer parameters and delivers over 4X throughput plus 5X energy efficiency gains.
-
Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
FPGA hardware for event-graph NN achieves 92.7% accuracy on SHD dataset with fewer parameters than SOTA while outperforming prior FPGA SNNs.